arXiv subjects

Abhinav Kumar

Publications and source records attributed to Abhinav Kumar.

At least 73 records · Page 4Linked to original sources

arXiv2023

PrObeD: Proactive Object Detection Wrapper

Previous research in $2D$ object detection focuses on various tasks, including detecting objects in generic and camouflaged images. These works are regarded as passive works for object detection as they take the input image as is. However, convergence to global minima is not guaranteed to be optimal in neural networks; therefore, we argue that the trained weights in the object detector are not optimal. To rectify this problem, we propose a wrapper based on proactive schemes, PrObeD, which enhances the performance of these object detectors by learning a signal. PrObeD consists of an encoder-decoder architecture, where the encoder network generates an image-dependent signal termed templates to encrypt the input images, and the decoder recovers this template from the encrypted images. We propose that learning the optimum template results in an object detector with an improved detection performance. The template acts as a mask to the input images to highlight semantics useful for the object detector. Finetuning the object detector with these encrypted images enhances the detection performance for both generic and camouflaged. Our experiments on MS-COCO, CAMO, COD$10$K, and NC$4$K datasets show improvement over different detectors after applying PrObeD. Our models/codes are available at https://github.com/vishal3477/Proactive-Object-Detection.

cs.CV↗

arXiv2023

RL-based Variable Horizon Model Predictive Control of Multi-Robot Systems using Versatile On-Demand Collision Avoidance

Multi-robot systems have become very popular in recent years because of their wide spectrum of applications, ranging from surveillance to cooperative payload transportation. Model Predictive Control (MPC) is a promising controller for multi-robot control because of its preview capability and ability to handle constraints easily. The performance of the MPC widely depends on many parameters, among which the prediction horizon is the major contributor. Increasing the prediction horizon beyond a limit drastically increases the computation cost. Tuning the value of the prediction horizon can be very time-consuming, and the tuning process must be repeated for every task. Moreover, instead of using a fixed horizon for an entire task, a better balance between performance and computation cost can be established if different prediction horizons can be employed for every robot at each time step. Further, for such variable prediction horizon MPC for multiple robots, on-demand collision avoidance is the key requirement. We propose Versatile On-demand Collision Avoidance (VODCA) strategy to comply with the variable horizon model predictive control. We also present a framework for learning the prediction horizon for the multi-robot system as a function of the states of the robots using the Soft Actor-Critic (SAC) RL algorithm. The results are illustrated and validated numerically for different multi-robot tasks.

cs.RO↗

arXiv2023

Probing Classifiers are Unreliable for Concept Removal and Detection

Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Removing such concepts is non-trivial because of a complex relationship between the concept, text input, and the learnt representation. Recent work has proposed post-hoc and adversarial methods to remove such unwanted concepts from a model's representation. Through an extensive theoretical and empirical analysis, we show that these methods can be counter-productive: they are unable to remove the concepts entirely, and in the worst case may end up destroying all task-relevant features. The reason is the methods' reliance on a probing classifier as a proxy for the concept. Even under the most favorable conditions for learning a probing classifier when a concept's relevant features in representation space alone can provide 100% accuracy, we prove that a probing classifier is likely to use non-concept features and thus post-hoc or adversarial methods will fail to remove the concept correctly. These theoretical implications are confirmed by experiments on models trained on synthetic, Multi-NLI, and Twitter datasets. For sensitive applications of concept removal such as fairness, we recommend caution against using these methods and propose a spuriousness metric to gauge the quality of the final classifier.

cs.LG↗

arXiv2023

Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild

Recognizing scenes and objects in 3D from a single image is a longstanding goal of computer vision with applications in robotics and AR/VR. For 2D recognition, large datasets and scalable solutions have led to unprecedented advances. In 3D, existing benchmarks are small in size and approaches specialize in few object categories and specific domains, e.g. urban driving scenes. Motivated by the success of 2D recognition, we revisit the task of 3D object detection by introducing a large benchmark, called Omni3D. Omni3D re-purposes and combines existing datasets resulting in 234k images annotated with more than 3 million instances and 98 categories. 3D detection at such scale is challenging due to variations in camera intrinsics and the rich diversity of scene and object types. We propose a model, called Cube R-CNN, designed to generalize across camera and scene types with a unified approach. We show that Cube R-CNN outperforms prior works on the larger Omni3D and existing benchmarks. Finally, we prove that Omni3D is a powerful dataset for 3D object recognition and show that it improves single-dataset performance and can accelerate learning on new smaller datasets via pre-training.

cs.CV↗

arXiv2023

Range and strength of mechanical interactions of force dipoles in elastic fiber networks

Mechanical forces generated by myosin II molecular motors drive diverse cellular processes, most notably shape change, division and locomotion. These forces may be transmitted over long range through the cytoskeletal medium - a disordered, viscoelastic network of biopolymers. The resulting cell size scale force chains can in principle mediate mechanical interactions between distant actomyosin units, leading to self-organized structural order in the cell cytoskeleton. To investigate this process, we model the actin cytoskeleton on a percolated fiber lattice network, where fibers are modeled as linear elastic elements that can both bend and stretch, whereas myosin motors exert contractile force dipoles. We quantify the range and heterogeneity of force transmission in these networks in response to a force dipole, showing how these depend on varying bond dilution and fiber bending-to-stretching stiffness ratio. By analyzing clusters of nodes connected to highly strained bonds, as well as the decay rate of strain energy with distance from the force dipole, we show that long-range force transmission is screened out by fiber bending in diluted networks. We further characterize the difference in the propagation of tensile and compressive forces. This leads to a dependence of the mechanical interaction between a pair of force dipoles on their mutual separation and orientation. In more homogeneous networks, the interaction between force dipoles recapitulates the power law dependence on separation distance predicted by continuum elasticity theory, while in diluted networks, the interactions are short-ranged and fluctuate strongly with local network configurations. Altogether, our work suggests that elastic interactions between force dipoles in disordered, fibrous media can act as an organizing principle in biological materials.

cond-mat.soft↗

arXiv2022

Bounds on Power and Common Message Fractions for RSMA with Imperfect SIC

Rate-Splitting multiple access (RSMA) has emerged as a key enabler in improving the performance of the beyond fifth-generation (5G) cellular networks. The existing literature has typically considered the sum rate of the users to evaluate the performance of RSMA. However, it has been shown in the existing works that maximizing the sum rate can result in asymmetric user performance. It significantly enhances one user's rate at the cost of the rate of another RSMA user. Further, imperfections can reduce the performance of successive interference cancellation (SIC)-based RSMA. Therefore, in this letter, we consider the imperfection in SIC and derive suitable bounds on fractions of the power allocated for common and private messages and the fraction of common message intended for each user in an RSMA pair such that their individual RSMA rates are greater than their respective orthogonal multiple access (OMA) rates. Through simulations, we validate the derived bounds. We show that they can be used to appropriately select the RSMA parameters resulting in users' RSMA rates being better than their respective OMA rates.

eess.SP↗

arXiv2022

Adaptive Multi-User Clustering and Power Allocation for NOMA Systems with Imperfect SIC

Non-orthogonal multiple access (NOMA) is recognized as a promising radio access technique for the next generation wireless systems. We consider a practical downlink NOMA system with imperfect successive interference cancellation and derive bounds on the power allocation factors for a given number of users in each cluster. We propose a minimum signal-to-interference-plus-noise ratio difference criterion between two successive NOMA users in a cluster of users to achieve higher rates than an equivalent orthogonal multiple access (OMA) system. We then propose adaptive multi-user clustering and power allocation algorithms for downlink NOMA systems. Through extensive simulations, we show that the proposed algorithms achieve higher rates than the state-of-the-art algorithms.

eess.SP↗

arXiv2022

Disentangling Mixtures of Unknown Causal Interventions

In many real-world scenarios, such as gene knockout experiments, targeted interventions are often accompanied by unknown interventions at off-target sites. Moreover, different units can get randomly exposed to different unknown interventions, thereby creating a mixture of interventions. Identifying different components of this mixture can be very valuable in some applications. Motivated by such situations, in this work, we study the problem of identifying all components present in a mixture of interventions on a given causal Bayesian Network. We construct an example to show that, in general, the components are not identifiable from the mixture distribution. Next, assuming that the given network satisfies a positivity condition, we show that, if the set of mixture components satisfy a mild exclusion assumption, then they can be uniquely identified. Our proof gives an efficient algorithm to recover these targets from the exponentially large search space of possible targets. In the more realistic scenario, where distributions are given via finitely many samples, we conduct a simulation study to analyze the performance of an algorithm derived from our identifiability proof.

stat.ML↗

arXiv2022

Reference Resolution and Context Change in Multimodal Situated Dialogue for Exploring Data Visualizations

Reference resolution, which aims to identify entities being referred to by a speaker, is more complex in real world settings: new referents may be created by processes the agents engage in and/or be salient only because they belong to the shared physical setting. Our focus is on resolving references to visualizations on a large screen display in multimodal dialogue; crucially, reference resolution is directly involved in the process of creating new visualizations. We describe our annotations for user references to visualizations appearing on a large screen via language and hand gesture and also new entity establishment, which results from executing the user request to create a new visualization. We also describe our reference resolution pipeline which relies on an information-state architecture to maintain dialogue context. We report results on detecting and resolving references, effectiveness of contextual information on the model, and under-specified requests for creating visualizations. We also experiment with conventional CRF and deep learning / transformer models (BiLSTM-CRF and BERT-CRF) for tagging references in user utterance text. Our results show that transfer learning significantly boost performance of the deep learning methods, although CRF still out-performs them, suggesting that conventional methods may generalize better for low resource data.

cs.CL↗

arXiv2022

DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

Modern neural networks use building blocks such as convolutions that are equivariant to arbitrary 2D translations. However, these vanilla blocks are not equivariant to arbitrary 3D translations in the projective manifold. Even then, all monocular 3D detectors use vanilla blocks to obtain the 3D coordinates, a task for which the vanilla blocks are not designed for. This paper takes the first step towards convolutions equivariant to arbitrary 3D translations in the projective manifold. Since the depth is the hardest to estimate for monocular detection, this paper proposes Depth EquiVarIAnt NeTwork (DEVIANT) built with existing scale equivariant steerable blocks. As a result, DEVIANT is equivariant to the depth translations in the projective manifold whereas vanilla networks are not. The additional depth equivariance forces the DEVIANT to learn consistent depth estimates, and therefore, DEVIANT achieves state-of-the-art monocular 3D detection results on KITTI and Waymo datasets in the image-only category and performs competitively to methods using extra information. Moreover, DEVIANT works better than vanilla networks in cross-dataset evaluation. Code and models at https://github.com/abhi1kumar/DEVIANT

cs.CV↗

arXiv2022

Universal optimality of the $E_8$ and Leech lattices and interpolation formulas

We prove that the $E_8$ root lattice and the Leech lattice are universally optimal among point configurations in Euclidean spaces of dimensions $8$ and $24$, respectively. In other words, they minimize energy for every potential function that is a completely monotonic function of squared distance (for example, inverse power laws or Gaussians), which is a strong form of robustness not previously known for any configuration in more than one dimension. This theorem implies their recently shown optimality as sphere packings, and broadly generalizes it to allow for long-range interactions. The proof uses sharp linear programming bounds for energy. To construct the optimal auxiliary functions used to attain these bounds, we prove a new interpolation theorem, which is of independent interest. It reconstructs a radial Schwartz function $f$ from the values and radial derivatives of $f$ and its Fourier transform $\widehat{f}$ at the radii $\sqrt{2n}$ for integers $n\ge1$ in $\mathbb{R}^8$ and $n \ge 2$ in $\mathbb{R}^{24}$. To prove this theorem, we construct an interpolation basis using integral transforms of quasimodular forms, generalizing Viazovska's work on sphere packing and placing it in the context of a more conceptual theory.

math.MG↗

arXiv2022

$α$-Fairness User Pairing for Downlink NOMA Systems with Imperfect Successive Interference Cancellation

Non-orthogonal multiple access (NOMA) is considered as one of the predominant multiple access technique for the next-generation cellular networks. We consider a 2-user pair downlink NOMA system with imperfect successive interference cancellation (SIC). We consider bounds on the power allocation factors and then formulate the power allocation as an optimization problem to achieve {$α$-Fairness} among the paired users. We show that {$α$-Fairness} based power allocation factor coincides with lower bound on power allocation factor in case of perfect SIC and $α> 2$. Further, as long as the proposed criterion is satisfied, it converges to the upper bound with increasing imperfection in SIC. Similarly, we show that, for $0<α<1$, the optimal power allocation factor coincides with the derived lower bound on power allocation. Based on these observations, we then propose a low complexity sub-optimal algorithm. Through extensive simulations, we analyse the performance of the proposed algorithm and compare the performance against the state-of-the-art algorithms. We show that even though Near-Far based pairing achieves better fairness than the proposed algorithms, it fails to achieve rates equivalent to its orthogonal multiple access counterparts with increasing imperfections in SIC. Further, we show that the proposed optimal and sub-optimal algorithms achieve significant improvements in terms of fairness as compared to the state-of-the-art algorithms.

eess.SP↗

arXiv2022

Impact of NOMA and CoMP Implementation Order on the Performance of Ultra-Dense Networks

Non-orthogonal multiple access (NOMA) is a promising multiple access technology to improve the throughput and spectral efficiency of the users for 5G and beyond cellular networks. Similarly, coordinated multi-point transmission and reception (CoMP) is an existing technology to improve the coverage of cell-edge users. Hence, NOMA along with CoMP can potentially enhance the throughput and coverage of the users. However, the order of implementation of CoMP and NOMA can have a significant impact on the system performance of Ultra-dense networks (UDNs). Motivated by this, we study the performance of the CoMP and NOMA based UDN by proposing two kinds of user grouping and pairing schemes that differ in the order in which CoMP and NOMA are performed for a group of users. Detailed simulation results are presented comparing the proposed schemes with the state-of-the-art systems with varying user and base station densities. Through numerical results, we show that the proposed schemes can be used to achieve a suitable coverage-throughout trade-off in UDNs.

eess.SP↗

arXiv2022

Spectral and Energy Efficient User Pairing for RIS-assisted Uplink NOMA Systems with Imperfect Phase Compensation

Non-orthogonal multiple access (NOMA) is considered a key technology for improving the spectral efficiency of fifth-generation (5G) and beyond 5G cellular networks. NOMA is beneficial when the channel vectors of the users are in the same direction, which is not always possible in conventional wireless systems. With the help of a reconfigurable intelligent surface (RIS), the base station can control the directions of the channel vectors of the users. Thus, by combining both technologies, the RIS-assisted NOMA systems are expected to achieve greater improvements in the network throughput. However, ideal phase control at the RIS is unrealizable in practice because of the imperfections in the channel estimations and the hardware limitations. This imperfection in phase control can have a significant impact on the system performance. Motivated by this, in this paper, we consider an RIS-assisted uplink NOMA system in the presence of imperfect phase compensation. We formulate the criterion for pairing the users that achieves minimum required data rates. We propose adaptive user pairing algorithms that maximize spectral or energy efficiency. We then derive various bounds on power allocation factors for the paired users. Through extensive simulation results, we show that the proposed algorithms significantly outperform the state-of-the-art algorithms in terms of spectral and energy efficiency.

cs.IT↗

arXiv2021

How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI

Many real-world problems require the combined application of multiple reasoning abilities employing suitable abstractions, commonsense knowledge, and creative synthesis of problem-solving strategies. To help advance AI systems towards such capabilities, we propose a new reasoning challenge, namely Fermi Problems (FPs), which are questions whose answers can only be approximately estimated because their precise computation is either impractical or impossible. For example, "How much would the sea level rise if all ice in the world melted?" FPs are commonly used in quizzes and interviews to bring out and evaluate the creative reasoning abilities of humans. To do the same for AI systems, we present two datasets: 1) A collection of 1k real-world FPs sourced from quizzes and olympiads; and 2) a bank of 10k synthetic FPs of intermediate complexity to serve as a sandbox for the harder real-world challenge. In addition to question answer pairs, the datasets contain detailed solutions in the form of an executable program and supporting facts, helping in supervision and evaluation of intermediate steps. We demonstrate that even extensively fine-tuned large scale language models perform poorly on these datasets, on average making estimates that are off by two orders of magnitude. Our contribution is thus the crystallization of several unsolved AI problems into a single, new challenge that we hope will spur further advances in building systems that can reason.

cs.CL↗

arXiv2021

Enhanced User Grouping and Pairing Scheme for CoMP-NOMA-based Cellular Networks

Non-orthogonal multiple access (NOMA) has been identified as one of the promising technologies to enhance the spectral efficiency and throughput for the fifth generation (5G) and beyond 5G cellular networks. Alternatively, Coordinated multi-point transmission and reception (CoMP) improves the cell edge users' coverage. Thus, CoMP and NOMA can be used together to improve the overall coverage and throughput of the users. However, user grouping and pairing for CoMP-NOMA-based cellular networks have not been suitably studied in the existing literature. Motivated by this, we propose a user grouping and pairing scheme for a CoMP-NOMA-based system. Detailed numerical results are presented comparing the proposed scheme with the purely OMA-based benchmark system, NOMA only, and CoMP only systems. We show through simulation results that the proposed scheme offers a trade-off between throughput and coverage as compared to the existing NOMA or CoMP based system.

cs.IT↗

arXiv2021

Scaling Up Exact Neural Network Compression by ReLU Stability

We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable. However, current approaches to determine the stability of neurons with Rectified Linear Unit (ReLU) activations require solving or finding a good approximation to multiple discrete optimization problems. In this work, we introduce an algorithm based on solving a single optimization problem to identify all stable neurons. Our approach is on median 183 times faster than the state-of-art method on CIFAR-10, which allows us to explore exact compression on deeper (5 x 100) and wider (2 x 800) networks within minutes. For classifiers trained under an amount of L1 regularization that does not worsen accuracy, we can remove up to 56% of the connections on the CIFAR-10 dataset. The code is available at the following link, https://github.com/yuxwind/ExactCompression.

cs.LG↗

arXiv2021

Understanding the ferromagnetic insulating state in Cr doped VO$_2$

Experimentally Cr doping in the rutile phase of VO$_2$ is found to stabilize a charge ordered ferromagnetic insulating state in the doping range of 10\% to 20\%. In this work, we investigated its origin at 12.5\% Cr doping using a combination of ab-initio electronic structure calculations as well as microscopic modeling. Our calculations are found to reproduce the ferromagnetic insulating state as well as a charge ordering at the V and Cr sites. The mapping of the ab-initio band structure onto a tight-binding Hamiltonian allows one to calculate the energy gain from different exchange pathways. This gain is quantified in this work for the first time and the role of charge ordering in stabilizing a ferromagnetic insulating state is understood.

cond-mat.mtrl-sci↗